|
 “We’re trying to change how people run agronomic research.
Instead of establishing a small field plot, running statistics,
and publishing the means, what we’re trying to do involves the
farmer far more directly. We are running experiments with
farmers’ machinery in their own fields. We can detect
site-specific responses to different inputs. And we can see
whether there’s a response in different parts of the field,”
says Nicolas Martin, assistant professor in the Department of
Crop Sciences at Illinois and co-author of the study.
He adds, “We developed methodology using deep learning to
generate yield predictions. It incorporates information from
different topographic variables, soil electroconductivity, as
well as nitrogen and seed rate treatments we applied throughout
nine Midwestern corn fields.”
Martin and his team worked with 2017 and 2018 data from the Data
Intensive Farm Management project, in which seeds and nitrogen
fertilizer were applied at varying rates across 226 fields in
the Midwest, Brazil, Argentina, and South Africa. On-ground
measurements were paired with high-resolution satellite images
from PlanetLab to predict yield.
Fields were digitally broken down into 5-meter (approximately
16-foot) squares. Data on soil, elevation, nitrogen application
rate, and seed rate were fed into the computer for each square,
with the goal of learning how the factors interact to predict
yield in that square.
The researchers approached their analysis with a type of machine
learning or artificial intelligence known as a convolutional
neural network (CNN). Some types of machine learning start with
patterns and ask the computer to fit new bits of data into those
existing patterns. Convolutional neural networks are blind to
existing patterns. Instead, they take bits of data and learn the
patterns that organize them, similar to the way humans organize
new information through neural networks in the brain. The CNN
process, which predicted yield with high accuracy, was also
compared to other machine learning algorithms and traditional
statistical techniques.
[to top of second column] |
“We don’t really know what is causing differences in
yield responses to inputs across a field. Sometimes people have an
idea that a certain spot should respond really strongly to nitrogen
and it doesn’t, or vice versa. The CNN can pick up on hidden
patterns that may be causing a response,” Martin says. “And when we
compared several methods, we found out that the CNN was working very
well to explain yield variation.”
Using artificial intelligence to untangle data from precision
agriculture is still relatively new, but Martin says his experiment
merely grazes the tip of the iceberg in terms of CNN’s potential
applications. “Eventually, we could use it to come up with optimum
recommendations for a given combination of inputs and site
constraints.”
The article, “Modeling yield response to crop management using
convolutional neural networks,” is published in Computers and
Electronics in Agriculture [DOI: 10.1016/j.compag.2019.105197].
Authors include Alexandre Barbosa, Rodrigo Trevisan, Naira
Hovakimyan, and Nicolas Martin. Barbosa and Hovakimyan are in the
Department of Mechanical Science and Engineering in the Grainger
College of Engineering at Illinois. Trevisan and Martin are in the
Department of Crop Sciences in the College of Agricultural, Consumer
and Environmental Sciences at Illinois.
The University of Illinois and the College of ACES are leading the
digital agriculture revolution with a new Center for Digital
Agriculture; first-of-their-kind majors combining computer science
and crop and animal sciences; the Data Intensive Farm Management
project; engineering of teachable agricultural robots; and many more
initiatives.
[Source: Nicolas Martin
News writer: Lauren Quinn] |
